Technology: Artificial Intelligence – How We Got Here by Richard Campbell



Artificial Intelligence is ascendant in computing today – but how did this happen? Join Richard Campbell as he explores the origins of AI going back to the 1950s.



source

Post Author: Global AI Community

1 thought on “Technology: Artificial Intelligence – How We Got Here by Richard Campbell

  • Cuòn Manh

    (October 18, 2020 - 10:22 am)

    The variance equation for linear combinations of random variables applies to the dot product which together with cosine angle is very useful. Eg. Noise sensitivity.
    ReLU is a switch. The electricty in your house is an AC sine wave. Turn on a light and the output of the switch is f(x)=x. The same sine wave as the input. Off f(x)=0. An ReLU can be on (connect) or off (disconnect) according to the binary predicate (x<0). A ReLU neural network then is a switched composition of dot products. If all the switch states are known there exists a linear mapping between the input vector and the output vector upon which various linear algebra metrics can be applied.
    Ultimately this leads you to high speed, low parameter count Fast Transform (fixed filter bank) neural networks.

Comments are closed.